mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-02 02:11:58 +00:00
e77c41e28d
- Replace monolithic `litellm` service with dedicated `ui` (nginx/Next.js, port 3000) and `gateway` (uvicorn/FastAPI, port 4000) services, each building from their own Dockerfile - Update prometheus.yml scrape target from `litellm:4000` → `gateway:4000` - Add litellm/proxy/_experimental/out/ to .gitignore and remove the 680 committed build artefacts; the UI bundle is now produced inside the Docker build, not checked in to source control - Add tests/test_litellm/test_docker_compose.py with 17 static checks covering service presence, build config, ports, env vars, health checks, dependencies, and prometheus scrape targets Resolves LIT-2815 https://claude.ai/code/session_01JVLLUH66aUXF9kxoHcYxWu
86 lines
3.1 KiB
YAML
86 lines
3.1 KiB
YAML
services:
|
|
ui:
|
|
build:
|
|
context: .
|
|
dockerfile: ui/Dockerfile
|
|
image: docker.litellm.ai/berriai/litellm-ui:main-stable
|
|
ports:
|
|
- "3000:3000" # Map the container port to the host, change the host port if necessary
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "wget -qO- http://localhost:3000/healthz || exit 1"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 20s
|
|
|
|
gateway:
|
|
build:
|
|
context: .
|
|
dockerfile: gateway/Dockerfile
|
|
image: docker.litellm.ai/berriai/litellm-gateway:main-stable
|
|
#########################################
|
|
## Uncomment these lines to start proxy with a config.yaml file ##
|
|
# volumes:
|
|
# - ./config.yaml:/app/config.yaml
|
|
# command:
|
|
# - "--config=/app/config.yaml"
|
|
##############################################
|
|
ports:
|
|
- "4000:4000" # Map the container port to the host, change the host port if necessary
|
|
environment:
|
|
DATABASE_URL: "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
|
|
# Optional: route read-only queries (find_*, count, group_by, query_raw/_first)
|
|
# to a separate reader endpoint, e.g. an Aurora reader. Leave unset for
|
|
# single-DB deployments. With IAM_TOKEN_DB_AUTH enabled, the reader URL
|
|
# is auto-refreshed alongside the writer.
|
|
# DATABASE_URL_READ_REPLICA: "postgresql://llmproxy:dbpassword9090@db-reader:5432/litellm"
|
|
STORE_MODEL_IN_DB: "True" # allows adding models to proxy via UI
|
|
env_file:
|
|
- .env # Load local .env file
|
|
depends_on:
|
|
- db # Indicates that this service depends on the 'db' service, ensuring 'db' starts first
|
|
healthcheck: # Defines the health check configuration for the container
|
|
test:
|
|
- CMD-SHELL
|
|
- python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:4000/health/liveliness')" # Command to execute for health check
|
|
interval: 30s # Perform health check every 30 seconds
|
|
timeout: 10s # Health check command times out after 10 seconds
|
|
retries: 3 # Retry up to 3 times if health check fails
|
|
start_period: 40s # Wait 40 seconds after container start before beginning health checks
|
|
|
|
db:
|
|
image: postgres:16
|
|
restart: always
|
|
container_name: litellm_db
|
|
environment:
|
|
POSTGRES_DB: litellm
|
|
POSTGRES_USER: llmproxy
|
|
POSTGRES_PASSWORD: dbpassword9090
|
|
ports:
|
|
- "5432:5432"
|
|
volumes:
|
|
- postgres_data:/var/lib/postgresql/data # Persists Postgres data across container restarts
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
|
|
interval: 1s
|
|
timeout: 5s
|
|
retries: 10
|
|
|
|
prometheus:
|
|
image: prom/prometheus
|
|
volumes:
|
|
- prometheus_data:/prometheus
|
|
- ./prometheus.yml:/etc/prometheus/prometheus.yml
|
|
ports:
|
|
- "9090:9090"
|
|
command:
|
|
- "--config.file=/etc/prometheus/prometheus.yml"
|
|
- "--storage.tsdb.path=/prometheus"
|
|
- "--storage.tsdb.retention.time=15d"
|
|
restart: always
|
|
|
|
volumes:
|
|
prometheus_data:
|
|
driver: local
|
|
postgres_data:
|
|
name: litellm_postgres_data # Named volume for Postgres data persistence
|